{"data":{"id":"e1606d54-1605-4c23-809e-e84280f98af5","title":"Differentially Private Zeroth-Order Methods for Scalable Large Language Model Fine-Tuning","summary":"This research proposes new methods for fine-tuning (customizing a trained AI model for specific tasks) large language models while protecting sensitive data using differential privacy (a technique that adds noise to data to prevent identifying individuals). The paper introduces DP-ZOSO and DP-ZOPO, which use zeroth-order gradient approximation (estimating how to improve the model without calculating exact mathematical directions) instead of traditional methods, making the process faster and more scalable while maintaining privacy protection.","solution":"N/A -- no mitigation discussed in source.","labels":["research","privacy"],"sourceUrl":"http://ieeexplore.ieee.org/document/11457969","publishedAt":"2026-03-30T13:17:27.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-03-30T13:17:27.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":"peer_reviewed","atlasIds":null}}